30. Mär 2020
Robustness guarantees for neural networks
Datum: 30. März 2020 |
Sprecher: Marta Kwiatkowska, Oxford University
Veranstaltungsort: Raiffeisen Lecture Hall, Central Building
Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to misclassify it. With potential applications including perception modules and end-to-end controllers for self-driving cars, this raises concerns about their safety. This lecture will describe progress with developing techniques to establish safety and probabilistic safety guarantees for deep neural networks, giving an overview of methods based on games, global optimisation and statistical approximation.